US10558841B2 - Method and apparatus for recognizing fingerprint ridge point - Google Patents
Method and apparatus for recognizing fingerprint ridge point Download PDFInfo
- Publication number
- US10558841B2 US10558841B2 US15/841,055 US201715841055A US10558841B2 US 10558841 B2 US10558841 B2 US 10558841B2 US 201715841055 A US201715841055 A US 201715841055A US 10558841 B2 US10558841 B2 US 10558841B2
- Authority
- US
- United States
- Prior art keywords
- pixel
- target pixel
- ridge
- fingerprint
- pixels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000005286 illumination Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
- G06V40/1359—Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
-
- G06K9/001—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G06K9/00013—
-
- G06K9/0008—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
- G06V40/1353—Extracting features related to minutiae or pores
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
- G06V40/1376—Matching features related to ridge properties or fingerprint texture
Definitions
- the present disclosure relates to the field of image recognition technologies, and in particular, to a method and an apparatus for recognizing fingerprint ridge points.
- Fingerprints are unique, convenient to be checked, and durable over the life of an individual, and therefore have become a primary means for biometric identification.
- fingerprint recognition has becomes a very important technology of identity authentication.
- a fingerprint consists of ridges on the epidermis at the end of a person's finger. Two fingerprints usually have same general features, but minutia features of the two fingerprints would not be identical.
- Fingerprint ridges are not continuous, smooth or straight, but instead they are often terminal, bifurcated or bent. These ridge endings, bifurcations points, and bending points are referred to as “feature points”.
- Fingerprint recognition is a technology of performing identity authentication by comparing feature points of different fingerprints.
- a method for recognizing a fingerprint ridge point is particularly provided.
- One aspect of the present disclosure provides a method for recognizing a fingerprint ridge point.
- the method includes receiving an input fingerprint image; performing orientation field estimation on the fingerprint image; identifying a pixel in the fingerprint image as a target pixel; determining a ridge direction of the target pixel, obtained according to the orientation field estimation, and a normal direction perpendicular to the ridge direction; defining a rectangular region by using the target pixel as a central point, a length of the rectangular region being along the ridge direction, a width of the rectangular region being along the normal direction of perpendicular to the ridge, and the rectangular region comprising multiple pixel rows arranged in the normal direction; calculating a sum of grayscale values of pixels in each pixel row; and determining that the target pixel is a fingerprint ridge point when the sum of grayscale values corresponding to a pixel row that includes the target pixel is the minimum.
- the apparatus includes: a module for receiving a fingerprint image, configured to: receive an input fingerprint image, and perform orientation field estimation on the fingerprint image; a module for determining a pixel direction, configured to: traverse a pixel in the fingerprint image as a target pixel, and determine a ridge direction of the target pixel according to the orientation field estimation, and a normal direction perpendicular to the ridge direction; a module for selecting a reference pixel, configured to define a rectangular region by using the target pixel as a central point, a length of the rectangular region being along the ridge direction, a width of the rectangular region being along the normal direction of perpendicular to the ridge, and the rectangular region comprising multiple pixel rows arranged in the normal direction; and a module for determining a fingerprint ridge point, configured to: calculate a sum of grayscale values of pixels in each pixel row, and determine that the target pixel is a fingerprint ridge point when a sum of grayscale
- Another aspect of the present disclosure provides a computer readable media containing program instructions, when executed by one or more processor, the programs instructions perform a method for recognizing a fingerprint ridge point.
- the method includes: performing orientation field estimation on a fingerprint image; identifying a pixel in the fingerprint image as a target pixel; determining a ridge direction of the target pixel, obtained according to the orientation field estimation, and a normal direction perpendicular to the ridge direction; defining a rectangular region by using the target pixel as a central point, a length of the rectangular region being along the ridge direction, a width of the rectangular region being along the normal direction of perpendicular to the ridge, and the rectangular region comprising multiple pixel rows arranged in the normal direction; calculating a sum of grayscale values of pixels in each pixel row; and determining that the target pixel is a fingerprint ridge point when the sum of grayscale values corresponding to a pixel row that includes the target pixel is the minimum.
- pixels in the fingerprint image are traversed.
- a rectangular region is defined by using a traversed pixel as a central point. Lengthwise and widthwise extending directions of the rectangular region are respectively corresponding to a ridge direction and a normal direction of a target pixel, and the rectangular region includes multiple pixel rows arranged in the normal direction.
- a sum of grayscale values of pixels in each pixel row is calculated, and it is determined that the target pixel is a fingerprint ridge point when a sum of grayscale values corresponding to a pixel row that includes the target pixel is the minimum.
- both a grayscale value of a traversed pixel and a grayscale value of a pixel at an adjacent position of the traversed pixel are used as references, so that incorrectly determined noise is effectively eliminated, and recognition accuracy is improved.
- FIG. 1 is a flowchart of a method for recognizing a fingerprint ridge point according to an embodiment
- FIG. 2 is a schematic diagram of defining a rectangular region by using a target pixel as a central point according to an embodiment
- FIG. 3 is a schematic diagram of a grayscale value of each pixel in a pixel row in a rectangular region according to an embodiment
- FIG. 4 is a schematic diagram of a received fingerprint image according to an embodiment
- FIG. 5 is a schematic diagram of a binarized fingerprint ridge image has been performed according to an embodiment
- FIG. 6 is a schematic diagram of the definition of a ridge distance according to an embodiment
- FIG. 7 is a flowchart of a process of calculating a weighted sum as a sum of grayscale values of pixels in a pixel row according to an embodiment
- FIG. 8 is a schematic diagram of an apparatus for recognizing a fingerprint ridge point according to an embodiment.
- FIG. 9 is a schematic structural diagram of a computer device for performing the foregoing method for recognizing a fingerprint ridge point according to an embodiment.
- Detection of feature points in fingerprint recognition often depends on detection of fingerprint ridges. That is, the feature points are obtained by analyzing the fingerprint ridges. A collected fingerprint image is binarized to obtain fingerprint ridges according to the fingerprint image. Often, black pixels are used for fingerprint ridge points, and white pixels are used for background regions on two sides of fingerprint ridges, thereby facilitating recognition of feature points of a fingerprint.
- the binarization methods usually include a local binarization method based on Gabor filters and the like.
- a method based on Gabor filters When a method based on Gabor filters is used, local directions and ridge frequencies need to be accurately calculated. However, it is relatively difficult to accurately calculate local directions and ridge frequencies when preprocessing of some low-quality fingerprint images.
- a method for recognizing a fingerprint ridge point may be implemented by using a computer, and may be performed on a computer system that is based on the von Neumann architecture.
- the computer program may be a fingerprint recognition program.
- the computer system may be a terminal device such as a smartphone, a tablet computer, a palmtop computer, a notebook computer or a personal computer on which a fingerprint sensor is installed.
- the method includes the following steps.
- Step S 104 Identify a pixel in the fingerprint image as a target pixel, and determine a ridge direction, of the target pixel according to orientation field estimation and a normal direction perpendicular to the ridge direction.
- the fingerprint image may be collected by using a camera or other fingerprint image capturing devices.
- a user may put a finger on a glass panel of a fingerprint sensor, and an image collection device located below the glass panel may obtain a fingerprint image of the finger.
- a fingerprint image photographed by another device may be received, and fingerprint recognition can be performed on the obtained fingerprint image.
- illumination normalization is first performed on the fingerprint image.
- An objective of illumination normalization is to eliminate the impact of light on the fingerprint image during collection of the fingerprint image. That is, during collection of the fingerprint image, due to different light source locations or light intensities, some regions of the collected fingerprint image are relatively bright and some other regions are relatively dark, or the entire fingerprint image is relatively bright or dark. After illumination normalization is performed, the relatively bright or dark regions may be corrected, thereby eliminating the impact of light on the collected fingerprint image.
- illumination normalization may be implemented by using a method based on a feature subspace or a correction method based on histogram equalization.
- Orientation field estimation of the fingerprint image may be used to determine direction information of a ridge that passes through each pixel in the fingerprint image.
- the direction information of each point may be calculated based on gradient distribution of grayscale values of pixels. For example, if a difference between a grayscale value of a pixel and a grayscale value of a pixel adjacent to the pixel on the left or right side is relatively small, and a difference between the grayscale value of the pixel and a grayscale value of a pixel adjacent to the pixel on the upper or lower side is relatively large, a ridge direction is a horizontal direction from the left side to the right side of the pixel, and a normal direction perpendicular to the ridge direction is a vertical direction from the upper side to the lower side of the pixel.
- Step S 106 Define a rectangular region by using the target pixel as a central point, where lengthwise and widthwise extending directions of the rectangular region are respectively corresponding to the ridge direction and the normal direction of the target pixel, and the rectangular region includes multiple pixel rows arranged in the normal direction.
- a fingerprint image includes multiple pixels.
- the pixel A is identified as a target pixel.
- a direction formed by connecting pixels A 1 , A 2 , A, A 3 , and A 4 is a ridge direction of the pixel A obtained by performing orientation field estimation on the pixel A.
- a direction formed by connecting E, D, C, B, F, G, H, and I is a normal direction of the pixel A obtained by performing orientation field estimation on the pixel A.
- the ridge direction of the pixel A is perpendicular to the normal direction of the pixel A.
- a rectangular region defined by using the pixel A as a central point is a rectangular region formed by using E 1 , E 4 , 14 , and I 1 as vertices.
- Four sides of the rectangular region are: a long side formed by connecting pixels E 1 , D 1 , C 1 , B 1 , F 1 , G 1 , H 1 , and I 1 , a short side formed by connecting pixels E 1 , E 2 , E, E 3 , and E 4 , a long side formed by connecting pixels E 4 , D 4 , C 4 , B 4 , F 4 , G 4 , H 4 , and I 4 , and a short side formed by connecting pixels I 1 , I 2 , E, I 3 , and I 4 .
- multiple pixel rows arranged in the normal direction of the pixel A in the rectangle includes:
- a first pixel row E 1 , E 2 , E, E 3 , and E 4 ;
- a second pixel row D 1 , D 2 , D, D 3 , and D 4 ;
- a third pixel row C 1 , C 2 , C, C 3 , and C 4 ;
- a ninth pixel row I 1 , I 2 , I, I 3 , and I 4 .
- Step S 108 Calculate a sum of grayscale values of pixels in each pixel row, and determine that the target pixel is a fingerprint ridge point when a sum of grayscale values corresponding to a pixel row that includes the target pixel is the minimum.
- grayscale values of pixels included in the rectangle (E 1 , E 4 , I 4 , I 1 ) in FIG. 2 , and a sum of grayscale values of each pixel row is calculated:
- the sum of grayscale values of the pixels in the fifth pixel row is 57, and the fifth pixel row includes a target pixel A. That is, the sum of grayscale values corresponding to the pixel row that includes the target pixel A is the minimum of the sums of grayscale values corresponding to all the pixel rows. Therefore, it is determined that the target pixel A is a fingerprint ridge point.
- the pixels A 1 , A 2 , A 3 , and A 4 in the fifth pixel row are all pixels in the ridge direction of the target pixel A. Pixels in another pixel row, for example, B 1 , B 2 , B, B 3 , and B 4 in the fourth pixel row, are also in the ridge direction, and form a pixel row that is adjacent and parallel to the fifth pixel row in the normal direction. If the sum of grayscale values of the pixels in the fifth pixel row is less than the sum of grayscale values of the pixels in the fourth pixel row, it indicates that the color of the pixels in the fifth pixel row is generally darker than the color of the pixels in the fourth pixel row, so that the fifth pixel row better meets a feature of a fingerprint ridge. Therefore, a candidate fingerprint ridge formed by the fifth pixel row is definitely chosen over a candidate fingerprint ridge formed by the fourth pixel row as a fingerprint ridge.
- the target pixel A can be determined as a fingerprint ridge point in the fingerprint ridge.
- the rectangular region is defined, and the sums of grayscale values of the pixel rows are calculated and compared. Therefore, during determining of a fingerprint ridge point, not only the grayscale value of the target pixel A is used as a determining basis, but also a grayscale value of a pixel adjacent to the target pixel A in the ridge direction is used as a reference. For example, if a grayscale value of the target pixel A is relatively large but the grayscale values of A 1 , A 2 , A 3 , and A 4 are relatively small, a general sum of grayscale values of the fifth pixel row is relatively small. This indicates that the target pixel A may be noise data, but the target pixel A may still be determined as a fingerprint ridge point. Therefore, interference from noise is eliminated, and recognition accuracy is improved.
- step S 104 to step S 108 are sequentially performed until pixels in the entire fingerprint image are traversed
- fingerprint ridge points included in the fingerprint image can be determined.
- Grayscale values of fingerprint ridge points are set to a relatively large value (for example, 255), and grayscale values of pixels that are not fingerprint ridge points in the fingerprint image are set to a relatively small value (for example, 0), so that the fingerprint image is binarized, thereby facilitating the following recognition process of features included in the fingerprint image.
- FIG. 4 shows an input fingerprint image
- FIG. 5 is a binarized image generated by traversing all pixels in the input fingerprint image.
- a grayscale value of a fingerprint ridge point is 255
- a grayscale value of a non-fingerprint ridge point is 0 (that is, color negative processing is performed).
- the length of a long side of a rectangle may be set in advance.
- the step of defining a rectangular region by using the target pixel as a central point is: calculating an average ridge distance of the fingerprint image; and setting a first quantity of the pixel rows according to the average ridge distance.
- a distance between a ridge and an adjacent furrow of a fingerprint is usually defined as a fingerprint ridge distance.
- the length between the center of a ridge and the center of a furrow is usually calculated as the ridge distance. It is assumed that there are n ridges whose widths are respectively w 1 , . . . , w n in the fingerprint image, and the ridges are defined separated by n- 1 furrows whose widths are v 1 , . . . , v n .
- the average ridge distance (the ridge distance for short hereinafter) of the fingerprint image refers to an average value of ridge distances in a particular region.
- the size of a ridge distance depends on a structure of the fingerprint and the resolution of image collection. In the fingerprint image, when a ridge distance is larger, it indicates that ridges there are sparser. In contrast, when a ridge distance is smaller, it indicates that ridges there are denser.
- the average ridge distance may be obtained by estimating ridge frequency.
- Methods for estimating the ridge distance include a geometric method and a spectral analysis method.
- a method proposed by Yilong Yin may be used, and in the method, a ridge distance is estimated based on a statistics window.
- a method proposed by En Zhu may be used, and in the method, local regions are projected on a curve that passes through the centers of the regions, where tangential directions of all points are perpendicular to the ridge direction. In this way, the average ridge distance of the entire image is calculated.
- the setting a first quantity of the pixel rows according to the average ridge distance may be specifically: setting the first quantity of the pixel rows to be less than a quantity of pixels corresponding to the average ridge distance.
- the defined rectangular region extends greatly in the normal direction of the target pixel A.
- the rectangular region may extend across two ridges. Consequently, pixels in a paralleled fingerprint ridge affect the determining of the target pixel A.
- the defined rectangular region may not cover multiple ridges in the normal direction of the target pixel A. Therefore, interference from another ridge is eliminated, and the accuracy of a binarized image is improved.
- a second quantity of pixels included in each pixel row may be set according to a quantity of the pixel rows.
- a value of the second quantity may be 1 ⁇ 3 to 2 ⁇ 3 of that of the first quantity.
- a quantity of pixels selected in the ridge direction of the target pixel may be less than pixels selected in the normal direction of the target pixel. That is, a side, extending in the normal direction of the target pixel, of the rectangular region is the long side of the rectangular region, and a side, extending in the ridge direction of the target pixel, of the rectangular region is the short side of the rectangular region.
- the length of the short side may be selected to be between 1 ⁇ 3 and 2 ⁇ 3 of the length of the long side.
- the second quantity is set to be relatively large, determining of a target pixel at a position where a fingerprint ridge bends sharply is easily interfered with by another fingerprint ridge point in the bent ridge. If the second quantity is set to be relatively small, a quantity of adjacent reference pixels on which the determining of the target pixel that is incorrectly collected as noise depends is reduced. Therefore, the target pixel that is incorrectly collected as the digital noise is easily ignored. If the value of the second quantity is set to be 1 ⁇ 3 to 2 ⁇ 3 of that of the first quantity, a balance can be reached between the first quantity and the second quantity, so that the accuracy of binarization is improved.
- a corresponding weight coefficient is set for each pixel in the pixel row, and a weighted sum is calculated according to weight coefficients as the sum of grayscale values of pixels in the pixel row.
- the method includes the following steps.
- Step S 202 Traverse pixel rows, and identify a traversed pixel row as a target pixel row.
- Step S 204 Determine grayscale values of pixels in the traversed pixel row that is used as the target pixel row and corresponding weight coefficients.
- Step S 206 Multiply the grayscale values of the pixels in the traversed pixel row by the corresponding weight coefficients, and add the products to obtain a weighted sum.
- the sum of grayscale values of the first pixel row E 1 , E 2 , E, E 3 , and E 4 is: 79 ⁇ b 1 +45 ⁇ b 2 +83 ⁇ b 3 +84 ⁇ b 2 +51 ⁇ b 1 .
- An appropriate weight coefficient is set in advance for a pixel at each position in the pixel row, so that proportions accounted for by the grayscale value of each pixel in the calculated sum of grayscale values of the pixel row may be changed, and the pixels at some positions in the pixel row may have a greater impact on the sum of grayscale values of the entire pixel row.
- the weight coefficients of the pixels in the target pixel row decrement with a distance from a central pixel in the target pixel row.
- the weight coefficient b 1 corresponding to E 1 and E 4 may be set to be less than the weight coefficient b 2 corresponding to E 2 and E 3 .
- the grayscale value of E has a relatively strong impact on determining of whether E is a fingerprint ridge point. Therefore, the weight coefficient b 2 corresponding to E 2 and E 3 may be set to be less than the weight coefficient b 3 corresponding to E.
- the weight coefficient of each pixel in the target pixel row is set in a manner in which weight coefficients decrement with a distance from the central pixel in the target pixel row.
- a grayscale value of a pixel that is relatively close to the central pixel in the target pixel row may have a relatively large impact on the sum of grayscale values of the target pixel row, and a grayscale value of a pixel that is relatively far from the central pixel in the target pixel row is enabled to have a relatively small impact on the sum of grayscale values of the target pixel row, thereby improving determining accuracy.
- a grayscale value of the target pixel may be determined. It is determined whether the grayscale value of the target pixel is greater than a threshold. If the grayscale value is greater than the threshold, it is determined that the target pixel is not a fingerprint ridge point.
- pre-estimation may be performed on the fingerprint image to directly determine that a pixel that clearly has a relatively large grayscale value is not a fingerprint ridge point. Therefore, the step of defining a rectangular region is omitted, thereby increasing a recognition speed.
- an apparatus for recognizing a fingerprint ridge point includes a module for receiving a fingerprint image 102 , a module for acquiring a pixel direction 104 , a module for selecting a reference pixel 106 , and a module for determining a fingerprint ridge point 108 .
- the module for receiving a fingerprint image 102 is configured to: receive an input fingerprint image, and perform orientation field estimation on the fingerprint image.
- the module for acquiring a pixel direction 104 is configured to: traverse a pixel in the fingerprint image as a target pixel, and determine a ridge direction, obtained according to orientation field estimation, of the target pixel and a normal direction perpendicular to the ridge direction.
- the module for selecting a reference pixel 106 is configured to: define a rectangular region by using the target pixel as a central point, where lengthwise and widthwise extending directions of the rectangular region are respectively corresponding to the ridge direction and the normal direction of the target pixel, and the rectangular region includes multiple pixel rows arranged in the normal direction.
- the module for determining a fingerprint ridge point 108 is configured to: calculate a sum of grayscale values of pixels in each pixel row, and determine that the target pixel is a fingerprint ridge point when a sum of grayscale values corresponding to a pixel row that includes the target pixel is the minimum.
- the module for selecting a reference pixel 106 is further configured to: calculate an average ridge distance of the fingerprint image, and set a first quantity of the pixel rows according to the average ridge distance.
- the module for selecting a reference pixel 106 is further configured to set, according to a quantity of the pixel rows, a second quantity of pixels included in each pixel row, where a value of the second quantity is 1 ⁇ 3 to 2 ⁇ 3 of that of the first quantity.
- the module for determining a fingerprint ridge point 108 is further configured to: traverse pixel rows, and identify a traversed pixel row as a target pixel row; determine grayscale values of pixels in the traversed pixel row that is used as the target pixel row and corresponding weight coefficients; and multiply the grayscale values of the pixels in the traversed pixel row by the corresponding weight coefficients, and add the products to obtain a weighted sum.
- the apparatus for recognizing a fingerprint ridge point further includes a pre-filtering module 110 , configured to: determine a grayscale value of the target pixel; determine whether the grayscale value of the target pixel is greater than a threshold; and if the grayscale value is greater than the threshold, determine that the target pixel is not a fingerprint ridge point.
- a pre-filtering module 110 configured to: determine a grayscale value of the target pixel; determine whether the grayscale value of the target pixel is greater than a threshold; and if the grayscale value is greater than the threshold, determine that the target pixel is not a fingerprint ridge point.
- pixels in the fingerprint image are traversed.
- a rectangular region is defined by using a traversed pixel as a central point. Lengthwise and widthwise extending directions of the rectangular region are respectively corresponding to a ridge direction and a normal direction of a target pixel, and the rectangular region includes multiple pixel rows arranged in the normal direction.
- a sum of grayscale values of pixels in each pixel row is calculated, and it is determined that the target pixel is a fingerprint ridge point when a sum of grayscale values corresponding to a pixel row that includes the target pixel is the minimum.
- both a grayscale value of a traversed pixel and a grayscale value of a pixel at an adjacent position of the traversed pixel are used as references, so that incorrectly determined noise is effectively eliminated, and recognition accuracy is improved.
- FIG. 9 shows a computer system 10 that is based on the von Neumann architecture and performs the foregoing method for recognizing a fingerprint ridge point.
- the computer system 10 may be a terminal device such as a smartphone, a tablet computer, a palmtop computer, a notebook computer or a personal computer.
- the computer system 10 may include an external input interface 1001 , a processor 1002 , a memory 1003 , and an output interface 1004 that are connected through a system bus.
- the external input interface 1001 may optionally include at least one of a mouse 10012 , a keyboard 10014 , a touchpad 10016 or a fingerprint sensor interface 10018 .
- the memory 1003 may include an external memory 10032 (for example a hard disk, an optical disk or a floppy disk) and an internal memory 10034 .
- the output interface 1004 may include devices such as a display screen 10042 and a speaker 10044 .
- the method is performed based on a computer program.
- a program file of the computer program may be stored in the external memory 10032 of the computer system 10 and is loaded to the internal memory 10034 when being run.
- the program file may then be compiled into machine code, and the machine code is transmitted to the processor 1002 and executed by the processor 1002 .
- a logic module for receiving a fingerprint image 102 a module for acquiring a pixel direction 104 , a module for selecting a reference pixel 106 , and a module for determining a fingerprint ridge point 108 may be formed in the computer system 10 , and implement their the functions as described in relation to FIG. 8 .
- input parameters may all be received by using the external input interface 1001 , transmitted to and cached in the memory 1003 , and then input to the processor 1002 to be processed.
- Result data of processing may be cached in the memory 1003 for subsequent processing, or may be transmitted to the output interface 1004 for output.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
- Image Analysis (AREA)
Abstract
Description
r i =w i/2+v i +w i+1/2.
79×b 1+45×b 2+83×b 3+84×b 2+51×b 1.
Claims (17)
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510566721.3A CN106503609B (en) | 2015-09-08 | 2015-09-08 | The recognition methods of fingerprint ridge point and device |
CN201510566721.3 | 2015-09-08 | ||
CN201510566721 | 2015-09-08 | ||
PCT/CN2016/079584 WO2017041488A1 (en) | 2015-09-08 | 2016-04-18 | Fingerprint ridge point recognition method and apparatus |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2016/079584 Continuation WO2017041488A1 (en) | 2015-09-08 | 2016-04-18 | Fingerprint ridge point recognition method and apparatus |
Publications (2)
Publication Number | Publication Date |
---|---|
US20180101710A1 US20180101710A1 (en) | 2018-04-12 |
US10558841B2 true US10558841B2 (en) | 2020-02-11 |
Family
ID=58239186
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/841,055 Active 2036-08-09 US10558841B2 (en) | 2015-09-08 | 2017-12-13 | Method and apparatus for recognizing fingerprint ridge point |
Country Status (6)
Country | Link |
---|---|
US (1) | US10558841B2 (en) |
EP (1) | EP3349140B1 (en) |
JP (1) | JP6487576B2 (en) |
KR (1) | KR101939936B1 (en) |
CN (1) | CN106503609B (en) |
WO (1) | WO2017041488A1 (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341482B (en) * | 2017-07-13 | 2020-07-10 | 海信视像科技股份有限公司 | Fingerprint identification method and device and computer readable storage medium |
CN109426795A (en) * | 2017-09-05 | 2019-03-05 | 比亚迪股份有限公司 | Fingerprint identification method and device |
EP3813015A4 (en) * | 2018-06-19 | 2021-08-18 | Sony Group Corporation | Information processing device, wearable equipment, information processing method, and program |
CN109976615B (en) * | 2019-03-28 | 2021-03-12 | Oppo广东移动通信有限公司 | Fingerprint image processing method and related device |
KR102223320B1 (en) * | 2019-08-13 | 2021-03-05 | 숭실대학교산학협력단 | Apparatus and method for determining status of vehicle LED lighting based on comparison of adjacent grayscale |
JP6927611B1 (en) * | 2020-03-16 | 2021-09-01 | Necプラットフォームズ株式会社 | Feature extraction device, feature extraction method, and program |
CN113408416B (en) * | 2021-06-18 | 2023-04-07 | 展讯通信(上海)有限公司 | Fingerprint frequency estimation method and device and fingerprint information extraction method and device |
CN113361448A (en) * | 2021-06-23 | 2021-09-07 | 浙江中正智能科技有限公司 | Method for detecting interference straight line in fingerprint image |
KR102614078B1 (en) * | 2021-12-22 | 2023-12-15 | 주식회사 라이프사이언스테크놀로지 | Apparatus and method of personal identification using biometric signal |
CN114445867B (en) * | 2022-02-21 | 2024-07-23 | 厦门天马微电子有限公司 | Fingerprint identifier and display device |
CN116935493B (en) * | 2023-09-13 | 2024-01-02 | 成都市青羊大数据有限责任公司 | Education management system |
CN117496560B (en) * | 2023-12-29 | 2024-04-19 | 深圳市魔力信息技术有限公司 | Fingerprint line identification method and device based on multidimensional vector |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6233348B1 (en) * | 1997-10-20 | 2001-05-15 | Fujitsu Limited | Fingerprint registering apparatus, fingerprint identifying apparatus, and fingerprint identifying method |
KR100391182B1 (en) | 2000-09-25 | 2003-07-16 | 주식회사 디토정보기술 | The method of a fingerprint minutia extraction using direct valley following |
US20040081360A1 (en) * | 2002-10-28 | 2004-04-29 | Lee Shih-Jong J. | Fast pattern searching |
US20050207627A1 (en) * | 2004-03-22 | 2005-09-22 | Lg Electronics Inc. | Fingerprint recognition system and method |
US20050264878A1 (en) * | 2003-06-17 | 2005-12-01 | Cross Match Technologies, Inc. | System for print imaging with prism illumination optics |
US20060153431A1 (en) * | 2003-01-06 | 2006-07-13 | Tatsunobu Ando | Fingerprint matching device and method, recording medium, and program |
CN101079102A (en) | 2007-06-28 | 2007-11-28 | 中南大学 | Fingerprint identification method based on statistic method |
EP2104059B1 (en) | 2008-03-14 | 2011-01-12 | NEC Corporation | Apparatus and method for processing image |
CN101996321A (en) | 2009-08-24 | 2011-03-30 | 北京易创科技有限公司 | Fingerprint recognition pretreatment method and device |
CN102510330A (en) | 2011-11-02 | 2012-06-20 | 杭州电子科技大学 | Novel fuzzy vault method based on fingerprint characteristic data and matching algorithm |
US20150063699A1 (en) * | 2013-08-30 | 2015-03-05 | Konica Minolta Laboratory U.S.A., Inc. | Line segmentation method applicable to document images containing handwriting and printed text characters or skewed text lines |
US9542585B2 (en) * | 2013-06-06 | 2017-01-10 | Apple Inc. | Efficient machine-readable object detection and tracking |
US20180018497A1 (en) * | 2015-02-13 | 2018-01-18 | Byd Company Limited | Method and device for calculating line distance |
US20180089484A1 (en) * | 2015-03-31 | 2018-03-29 | Nec Corporation | Biological pattern information processing device, biological pattern information processing method, and program |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2833313B2 (en) * | 1992-01-10 | 1998-12-09 | 富士通株式会社 | Authenticator for fingerprint feature points |
JP2725599B2 (en) * | 1994-06-21 | 1998-03-11 | 日本電気株式会社 | Ridge direction extraction device |
JP4020202B2 (en) * | 2003-06-16 | 2007-12-12 | 三菱電機株式会社 | Striped pattern extraction system and striped pattern extraction method |
JP4403513B2 (en) * | 2005-08-09 | 2010-01-27 | 日本電気株式会社 | Fingerprint ridge recognition device, fingerprint ridge recognition method, and program |
CN100470579C (en) * | 2007-09-21 | 2009-03-18 | 清华大学 | Certainty coding method and system in fingerprint identification |
JP5273801B2 (en) * | 2009-05-13 | 2013-08-28 | Necソフト株式会社 | Fingerprint feature point determination system, fingerprint feature point determination method, fingerprint feature point determination program |
-
2015
- 2015-09-08 CN CN201510566721.3A patent/CN106503609B/en active Active
-
2016
- 2016-04-18 WO PCT/CN2016/079584 patent/WO2017041488A1/en active Application Filing
- 2016-04-18 EP EP16843427.2A patent/EP3349140B1/en active Active
- 2016-04-18 JP JP2017558410A patent/JP6487576B2/en active Active
- 2016-04-18 KR KR1020177035024A patent/KR101939936B1/en active IP Right Grant
-
2017
- 2017-12-13 US US15/841,055 patent/US10558841B2/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6233348B1 (en) * | 1997-10-20 | 2001-05-15 | Fujitsu Limited | Fingerprint registering apparatus, fingerprint identifying apparatus, and fingerprint identifying method |
KR100391182B1 (en) | 2000-09-25 | 2003-07-16 | 주식회사 디토정보기술 | The method of a fingerprint minutia extraction using direct valley following |
US20040081360A1 (en) * | 2002-10-28 | 2004-04-29 | Lee Shih-Jong J. | Fast pattern searching |
US20060153431A1 (en) * | 2003-01-06 | 2006-07-13 | Tatsunobu Ando | Fingerprint matching device and method, recording medium, and program |
US20050264878A1 (en) * | 2003-06-17 | 2005-12-01 | Cross Match Technologies, Inc. | System for print imaging with prism illumination optics |
US20050207627A1 (en) * | 2004-03-22 | 2005-09-22 | Lg Electronics Inc. | Fingerprint recognition system and method |
CN101079102A (en) | 2007-06-28 | 2007-11-28 | 中南大学 | Fingerprint identification method based on statistic method |
EP2104059B1 (en) | 2008-03-14 | 2011-01-12 | NEC Corporation | Apparatus and method for processing image |
CN101996321A (en) | 2009-08-24 | 2011-03-30 | 北京易创科技有限公司 | Fingerprint recognition pretreatment method and device |
CN102510330A (en) | 2011-11-02 | 2012-06-20 | 杭州电子科技大学 | Novel fuzzy vault method based on fingerprint characteristic data and matching algorithm |
US9542585B2 (en) * | 2013-06-06 | 2017-01-10 | Apple Inc. | Efficient machine-readable object detection and tracking |
US20150063699A1 (en) * | 2013-08-30 | 2015-03-05 | Konica Minolta Laboratory U.S.A., Inc. | Line segmentation method applicable to document images containing handwriting and printed text characters or skewed text lines |
US20180018497A1 (en) * | 2015-02-13 | 2018-01-18 | Byd Company Limited | Method and device for calculating line distance |
US20180089484A1 (en) * | 2015-03-31 | 2018-03-29 | Nec Corporation | Biological pattern information processing device, biological pattern information processing method, and program |
Non-Patent Citations (3)
Title |
---|
Korean Intellectual Property Office (KIPO) Office Action 1 for 10-2017-7035024 dated Apr. 14, 2018 11 Pages (including translation). |
Ratha et al., Adaptive flow orientation based feature extraction in fingerprint images, Feb. 12, 1995. * |
The World Intellectual Property Organization (WIPO) International Search Report for PCT/CN2016/079584 dated Jul. 20, 2016 5 Pages (including translation). |
Also Published As
Publication number | Publication date |
---|---|
US20180101710A1 (en) | 2018-04-12 |
EP3349140A1 (en) | 2018-07-18 |
JP2018524663A (en) | 2018-08-30 |
KR20180003595A (en) | 2018-01-09 |
EP3349140B1 (en) | 2023-06-28 |
WO2017041488A1 (en) | 2017-03-16 |
CN106503609A (en) | 2017-03-15 |
JP6487576B2 (en) | 2019-03-20 |
KR101939936B1 (en) | 2019-01-17 |
CN106503609B (en) | 2019-07-16 |
EP3349140A4 (en) | 2019-04-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10558841B2 (en) | Method and apparatus for recognizing fingerprint ridge point | |
Raghavendra et al. | Novel image fusion scheme based on dependency measure for robust multispectral palmprint recognition | |
US9633269B2 (en) | Image-based liveness detection for ultrasonic fingerprints | |
US11874907B2 (en) | Method for enhancing fingerprint image, identifying fingerprint and starting-up application program | |
US8401250B2 (en) | Detecting objects of interest in still images | |
CN110287791B (en) | Screening method and system for face pictures | |
WO2020244071A1 (en) | Neural network-based gesture recognition method and apparatus, storage medium, and device | |
CN112418150B (en) | Palm vein image evaluation method, palm vein image evaluation device, computer equipment and storage medium | |
WO2022237397A1 (en) | Method and apparatus for evaluating image authenticity, computer device, and storage medium | |
US20160379038A1 (en) | Valid finger area and quality estimation for fingerprint imaging | |
US11475707B2 (en) | Method for extracting image of face detection and device thereof | |
CN109543686B (en) | Character recognition preprocessing binarization method based on self-adaptive multi-threshold | |
WO2016192213A1 (en) | Image feature extraction method and device, and storage medium | |
US11869271B2 (en) | Electronic apparatus and method of processing fingerprint image | |
EP3125194B1 (en) | Biometric authentication device, biometric authentication method, and program | |
US10140509B2 (en) | Information processing for detection and distance calculation of a specific object in captured images | |
CN112907206B (en) | Business auditing method, device and equipment based on video object identification | |
CN112801034A (en) | Finger vein recognition device | |
JP2019121187A (en) | Image processing apparatus, image processing method, and image processing program | |
US10825144B2 (en) | Image processing apparatus and image processing method | |
KR100675000B1 (en) | Apparatus and method for preprocessing fingerprint image | |
CN112861756A (en) | Finger vein identification method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, CHINA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:WANG, HONGFA;REEL/FRAME:044390/0407 Effective date: 20171207 Owner name: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, CHI Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:WANG, HONGFA;REEL/FRAME:044390/0407 Effective date: 20171207 |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: AWAITING TC RESP., ISSUE FEE NOT PAID |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |